agentleFS
milad-ahmdmilad-ahmd/agent-skills/skills/influencer-outreach/SKILL.md

influencer-outreach

Skill5 starsChanged 18 days agoMITView on GitHub

Plans and runs creator and influencer marketing campaigns on Instagram, TikTok, and YouTube, covering creator criteria and vetting, personalized outreach DMs and emails, follow-ups, briefs, deliverables, rate guidance, contracts checklist, disclosure rules, and performance tracking. Use when the user asks to find or contact influencers or creators, write outreach messages, or plan a UGC or influencer campaign.

5 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 5 edited versions we read keep these.

  • 1

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    No pressure tactics, no asking creators to hide sponsorship, and no buying fake engagement.

    line 42

“Common” is measured: kept by at least 6 in 10 of the 5 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Influencer Outreach

Creator partnerships that feel genuine, are fair to the creator and can be measured.

1. Campaign plan

The goal (awareness, content or UGC for ads, sales), budget, the product or offer, the platform, and the tier mix: nano (1–10k), micro (10–100k), mid (100k–500k), macro. Micro creators often have stronger engagement and trust per dollar, so recommend a mix.

2. Creator criteria and vetting

The audience must match the customer (location, age, interests). Check engagement quality (real comments, not just emoji), content quality and brand safety, consistency, past sponsorships and how they performed, and red flags for fake followers (sudden spikes, a bad follower-to-engagement ratio, generic comments). Output a scoring sheet (CSV): handle, platform, followers, average views, engagement estimate, niche fit (1–5), brand safety (1–5), notes, status. Finding creators: hashtag and keyword search, competitor tags, your own followers and customers who are creators, and creator marketplaces. The user does the browsing, or a connected tool does it.

3. Outreach

  • A personalised first DM or email of 120 words or fewer: a specific compliment about a real piece of their content, why they fit, the offer (paid, gifted or affiliate, stated clearly), and an easy next step.
  • 2 follow-ups (after 3–4 days and after 7 days), short and polite, and stop after that.
  • Templates for gifting-only, paid, affiliate and long-term ambassador deals.

4. Creator brief

The campaign goal, key messages (3 at most), do's and don'ts, deliverables (format, length, count, dates), usage rights and whitelisting, the CTA with a tracking link or code, the review process, and creative freedom (creators know their audience best).

5. Terms checklist

Deliverables, timeline, payment terms, usage rights and their duration, exclusivity, revisions, disclosure requirement and cancellation terms. Recommend a written contract and say clearly that this is not legal advice.

6. Tracking

UTM links or unique codes per creator. Track views, engagement, clicks, conversions, CPA, and content reused in ads. Do a post-campaign review to decide who to rebook.

Rules

  • Disclosure is mandatory: #ad or #sponsored and the platform's paid-partnership label (FTC, ASA and similar rules).
  • No pressure tactics, no asking creators to hide sponsorship, and no buying fake engagement.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.